{"total":63,"rows":[{"id":"2101.09624","title":"A Review of Speaker Diarization: Recent Advances with Deep Learning","created":"2021-01-24","cited_by_count":124,"area":null},{"id":"2111.14448","title":"AVA-AVD: Audio-Visual Speaker Diarization in the Wild","created":"2021-11-29","cited_by_count":25,"area":null},{"id":"2110.03151","title":"Transcribe-to-Diarize: Neural Speaker Diarization for Unlimited Number of Speakers using End-to-End Speaker-Attributed ASR","created":"2021-10-07","cited_by_count":22,"area":null},{"id":"2401.03506","title":"DiarizationLM: Speaker Diarization Post-Processing with Large Language Models","created":"2024-01-07","cited_by_count":16,"area":null},{"id":"2107.01545","title":"Towards Neural Diarization for Unlimited Numbers of Speakers Using Global and Local Attractors","created":"2021-07-04","cited_by_count":15,"area":null},{"id":"2409.06656","title":"Sortformer: A Novel Approach for Permutation-Resolved Speaker Supervision in Speech-to-Text Systems","created":"2024-09-10","cited_by_count":15,"area":null},{"id":"2204.03793","title":"Personal VAD 2.0: Optimizing Personal Voice Activity Detection for On-Device Speech Recognition","created":"2022-04-08","cited_by_count":12,"area":null},{"id":"2203.15974","title":"Multi-scale Speaker Diarization with Dynamic Scale Weighting","created":"2022-03-30","cited_by_count":11,"area":null},{"id":"2107.02852","title":"A Comparative Study of Modular and Joint Approaches for Speaker-Attributed ASR on Monaural Long-Form Audio","created":"2021-07-06","cited_by_count":10,"area":null},{"id":"2210.13690","title":"Highly Efficient Real-Time Streaming and Fully On-Device Speaker Diarization with Multi-Stage Clustering","created":"2022-10-25","cited_by_count":10,"area":null},{"id":"2408.09215","title":"Generating Data with Text-to-Speech and Large-Language Models for Conversational Speech Recognition","created":"2024-08-17","cited_by_count":9,"area":null},{"id":"2408.14886","title":"The VoxCeleb Speaker Recognition Challenge: A Retrospective","created":"2024-08-27","cited_by_count":9,"area":null},{"id":"2206.02432","title":"Online Neural Diarization of Unlimited Numbers of Speakers Using Global and Local Attractors","created":"2022-06-06","cited_by_count":8,"area":null},{"id":"2103.10661","title":"USTC-NELSLIP System Description for DIHARD-III Challenge","created":"2021-03-19","cited_by_count":7,"area":null},{"id":"2105.02096","title":"End-to-End Diarization for Variable Number of Speakers with Local-Global Networks and Discriminative Speaker Embeddings","created":"2021-05-05","cited_by_count":7,"area":null},{"id":"2208.13085","title":"Target Speaker Voice Activity Detection with Transformers and Its Integration with End-to-End Neural Diarization","created":"2022-08-27","cited_by_count":7,"area":null},{"id":"2203.16834","title":"A Comparative Study on Speaker-attributed Automatic Speech Recognition in Multi-party Meetings","created":"2022-03-31","cited_by_count":5,"area":null},{"id":"2210.14682","title":"In search of strong embedding extractors for speaker diarisation","created":"2022-10-26","cited_by_count":5,"area":null},{"id":"2104.02879","title":"Adapting Speaker Embeddings for Speaker Diarisation","created":"2021-04-07","cited_by_count":4,"area":null},{"id":"2306.02273","title":"End-to-End Joint Target and Non-Target Speakers ASR","created":"2023-06-04","cited_by_count":4,"area":null},{"id":"2306.12173","title":"Mixture Encoder for Joint Speech Separation and Recognition","created":"2023-06-21","cited_by_count":4,"area":null},{"id":"2409.00819","title":"LibriheavyMix: A 20,000-Hour Dataset for Single-Channel Reverberant Multi-Talker Speech Separation, ASR and Speaker Diarization","created":"2024-09-01","cited_by_count":4,"area":null},{"id":"2110.04694","title":"Multi-Channel End-to-End Neural Diarization with Distributed Microphones","created":"2021-10-10","cited_by_count":3,"area":null},{"id":"2202.04814","title":"Royalflush Speaker Diarization System for ICASSP 2022 Multi-channel Multi-party Meeting Transcription Challenge","created":"2022-02-10","cited_by_count":3,"area":null},{"id":"2208.08042","title":"The Conversational Short-phrase Speaker Diarization (CSSD) Task: Dataset, Evaluation Metric and Baselines","created":"2022-08-17","cited_by_count":3,"area":null},{"id":"2304.07842","title":"A Virtual Simulation-Pilot Agent for Training of Air Traffic Controllers","created":"2023-04-16","cited_by_count":3,"area":null},{"id":"2309.09180","title":"Neural Speaker Diarization Using Memory-Aware Multi-Speaker Embedding with Sequence-to-Sequence Architecture","created":"2023-09-17","cited_by_count":3,"area":null},{"id":"2312.16613","title":"Self-supervised Pretraining for Robust Personalized Voice Activity Detection in Adverse Conditions","created":"2023-12-27","cited_by_count":3,"area":null},{"id":"2403.06570","title":"Improving Speaker Assignment in Speaker-Attributed ASR for Real Meeting Applications","created":"2024-03-11","cited_by_count":3,"area":null},{"id":"2203.09767","title":"Speaker Embedding-aware Neural Diarization: an Efficient Framework for Overlapping Speech Diarization in Meeting Scenarios","created":"2022-03-18","cited_by_count":2,"area":null},{"id":"2303.12002","title":"End-to-End Integration of Speech Separation and Voice Activity Detection for Low-Latency Diarization of Telephone Conversations","created":"2023-03-21","cited_by_count":2,"area":null},{"id":"2305.19581","title":"SVVAD: Personal Voice Activity Detection for Speaker Verification","created":"2023-05-31","cited_by_count":2,"area":null},{"id":"2402.00067","title":"Online speaker diarization of meetings guided by speech separation","created":"2024-01-30","cited_by_count":2,"area":null},{"id":"2407.04444","title":"TokenVerse: Towards Unifying Speech and NLP Tasks via Transducer-based ASR","created":"2024-07-05","cited_by_count":2,"area":null},{"id":"2410.11243","title":"Investigation of Speaker Representation for Target-Speaker Speech Processing","created":"2024-10-15","cited_by_count":2,"area":null},{"id":"2501.17304","title":"Summary of the NOTSOFAR-1 Challenge: Highlights and Learnings","created":"2025-01-28","cited_by_count":2,"area":null},{"id":"2507.18161","title":"Recent Trends in Distant Conversational Speech Recognition: A Review of CHiME-7 and 8 DASR Challenges","created":"2025-07-24","cited_by_count":2,"area":null},{"id":"2509.26177","title":"Benchmarking Diarization Models","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2111.13694","title":"Speaker Embedding-aware Neural Diarization for Flexible Number of Speakers with Textual Information","created":"2021-11-28","cited_by_count":1,"area":null},{"id":"2210.14653","title":"TSUP Speaker Diarization System for Conversational Short-phrase Speaker Diarization Challenge","created":"2022-10-26","cited_by_count":1,"area":null},{"id":"2303.05397","title":"TOLD: A Novel Two-Stage Overlap-Aware Framework for Speaker Diarization","created":"2023-03-08","cited_by_count":1,"area":null},{"id":"2308.02160","title":"Speaker Diarization of Scripted Audiovisual Content","created":"2023-08-04","cited_by_count":1,"area":null},{"id":"2309.08489","title":"Towards Word-Level End-to-End Neural Speaker Diarization with Auxiliary Network","created":"2023-09-15","cited_by_count":1,"area":null},{"id":"2401.03473","title":"ICMC-ASR: The ICASSP 2024 In-Car Multi-Channel Automatic Speech Recognition Challenge","created":"2024-01-07","cited_by_count":1,"area":null},{"id":"2406.09443","title":"Comparative Analysis of Personalized Voice Activity Detection Systems: Assessing Real-World Effectiveness","created":"2024-06-12","cited_by_count":1,"area":null},{"id":"2409.13913","title":"Target word activity detector: An approach to obtain ASR word boundaries without lexicon","created":"2024-09-20","cited_by_count":1,"area":null},{"id":"2505.23207","title":"Towards Robust Overlapping Speech Detection: A Speaker-Aware Progressive Approach Using WavLM","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2104.02469","title":"Speaker Diarization using Two-pass Leave-One-Out Gaussian PLDA Clustering of DNN Embeddings","created":"2021-04-06","cited_by_count":0,"area":null},{"id":"2106.14371","title":"Sparsely Overlapped Speech Training in the Time Domain: Joint Learning of Target Speech Separation and Personal VAD Benefits","created":"2021-06-28","cited_by_count":0,"area":null},{"id":"2202.04855","title":"The USTC-Ximalaya system for the ICASSP 2022 multi-channel multi-party meeting transcription (M2MeT) challenge","created":"2022-02-10","cited_by_count":0,"area":null},{"id":"2302.09991","title":"Towards Measuring and Scoring Speaker Diarization Fairness","created":"2023-02-20","cited_by_count":0,"area":null},{"id":"2312.16002","title":"The NUS-HLT System for ICASSP2024 ICMC-ASR Grand Challenge","created":"2023-12-26","cited_by_count":0,"area":null},{"id":"2406.16315","title":"Song Data Cleansing for End-to-End Neural Singer Diarization Using Neural Analysis and Synthesis Framework","created":"2024-06-24","cited_by_count":0,"area":null},{"id":"2407.01317","title":"Leveraging Speaker Embeddings in End-to-End Neural Diarization for Two-Speaker Scenarios","created":"2024-07-01","cited_by_count":0,"area":null},{"id":"2501.03184","title":"Noise-Robust Target-Speaker Voice Activity Detection Through Self-Supervised Pretraining","created":"2025-01-06","cited_by_count":0,"area":null},{"id":"2506.12672","title":"SC-SOT: Conditioning the Decoder on Diarized Speaker Information for End-to-End Overlapped Speech Recognition","created":"2025-06-15","cited_by_count":0,"area":null},{"id":"2508.06393","title":"Robust Target Speaker Diarization and Separation via Augmented Speaker Embedding Sampling","created":"2025-08-08","cited_by_count":0,"area":null},{"id":"2509.14632","title":"Mitigating Intra-Speaker Variability in Diarization with Style-Controllable Speech Augmentation","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2510.12947","title":"HyWA: Architecture-Preserving Personalized Voice Activity Detection for Full-Duplex Voice Assistants","created":"2025-10-14","cited_by_count":0,"area":null},{"id":"2601.22792","title":"CALM: Joint Contextual Acoustic-Linguistic Modeling for Personalization of Multi-Speaker ASR","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2603.13379","title":"A Hierarchical End-of-Turn Model with Primary Speaker Segmentation for Real-Time Conversational AI","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2603.22709","title":"Who Spoke What When? Evaluating Spoken Language Models for Conversational ASR with Semantic and Overlap-Aware Metrics","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2609.38491","title":"Role-guided Speaker Deletion Verification in Clinical Psychiatry Speech Recordings with Audio Language Models","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}